INDEX

Explanations

code snippets, particularly indentation/whitespace

oai_token-act-pair · gemini-2.0-flash

code and legal text

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.54

audiovisuel

-0.53

PANY

-0.53

tahu

-0.51

 становника

-0.49

IKAN

-0.49

HasIndex

-0.49

UGHS

-0.49

bague

-0.48

 Equals

-0.48

POSITIVE LOGITS

<bos>

2.61

’

0.68

/**

0.66

 Савезне

0.63

 Administrativna

0.60

ніципа

0.57

mbic

0.56

Autoritní

0.54

 autorytatywna

0.53

Activations Density 0.517%

code snippets, particularly indentation/whitespace

code and legal text

No Comments

No Known Activations